blob: b026308126e655aa860efefbfa9a2a5262e07f46 (
plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
|
/*
* Copyright (c) 2009 Petri Lehtinen <petri@digip.org>
*
* Jansson is free software; you can redistribute it and/or modify
* it under the terms of the MIT license. See LICENSE for details.
*/
#include "../config.h"
int
utf8_encode (int codepoint, char *buffer, int *size)
{
if (codepoint < 0)
return -1;
else if (codepoint < 0x80) {
buffer[0] = (char)codepoint;
*size = 1;
}
else if (codepoint < 0x800) {
buffer[0] = 0xC0 + ((codepoint & 0x7C0) >> 6);
buffer[1] = 0x80 + ((codepoint & 0x03F));
*size = 2;
}
else if (codepoint < 0x10000) {
buffer[0] = 0xE0 + ((codepoint & 0xF000) >> 12);
buffer[1] = 0x80 + ((codepoint & 0x0FC0) >> 6);
buffer[2] = 0x80 + ((codepoint & 0x003F));
*size = 3;
}
else if (codepoint <= 0x10FFFF) {
buffer[0] = 0xF0 + ((codepoint & 0x1C0000) >> 18);
buffer[1] = 0x80 + ((codepoint & 0x03F000) >> 12);
buffer[2] = 0x80 + ((codepoint & 0x000FC0) >> 6);
buffer[3] = 0x80 + ((codepoint & 0x00003F));
*size = 4;
}
else
return -1;
return 0;
}
int
utf8_check_first (char byte)
{
unsigned char u = (unsigned char)byte;
if (u < 0x80)
return 1;
if (0x80 <= u && u <= 0xBF) {
/* second, third or fourth byte of a multi-byte
sequence, i.e. a "continuation byte" */
return 0;
}
else if (u == 0xC0 || u == 0xC1) {
/* overlong encoding of an ASCII byte */
return 0;
}
else if (0xC2 <= u && u <= 0xDF) {
/* 2-byte sequence */
return 2;
}
else if (0xE0 <= u && u <= 0xEF) {
/* 3-byte sequence */
return 3;
}
else if (0xF0 <= u && u <= 0xF4) {
/* 4-byte sequence */
return 4;
}
else { /* u >= 0xF5 */
/* Restricted (start of 4-, 5- or 6-byte sequence) or invalid
UTF-8 */
return 0;
}
}
int
utf8_check_full (const char *buffer, int size)
{
int i, value = 0;
unsigned char u = (unsigned char)buffer[0];
if (size == 2) {
value = u & 0x1F;
}
else if (size == 3) {
value = u & 0xF;
}
else if (size == 4) {
value = u & 0x7;
}
else
return 0;
for (i = 1; i < size; i++) {
u = (unsigned char)buffer[i];
if (u < 0x80 || u > 0xBF) {
/* not a continuation byte */
return 0;
}
value = (value << 6) + (u & 0x3F);
}
if (value > 0x10FFFF) {
/* not in Unicode range */
return 0;
}
else if (0xD800 <= value && value <= 0xDFFF) {
/* invalid code point (UTF-16 surrogate halves) */
return 0;
}
else if ((size == 2 && value < 0x80) || (size == 3 && value < 0x800) || (size == 4 && value < 0x10000)) {
/* overlong encoding */
return 0;
}
return 1;
}
int
utf8_check_string (const char *string, int length)
{
int i;
if (length == -1)
length = strlen (string);
for (i = 0; i < length; i++) {
int count = utf8_check_first (string[i]);
if (count == 0)
return 0;
else if (count > 1) {
if (i + count > length)
return 0;
if (!utf8_check_full (&string[i], count))
return 0;
i += count - 1;
}
}
return 1;
}
|
